Study Research on the Identification of Elements and Path of Digital Economy Enabling the Construction of Modern Circulation System-Analysis based on BP neural network and fsQCA

Abstract

Abstract: Accelerating the empowerment of the circulation system modernization by the digital economy plays a significant role in constructing the new development pattern. Existing research has shortcomings in precisely identifying and combining key elements of the digital economy to effectively drive the modernization of the circulation system towards higher efficiency and intelligence. To address this, the article conducts an empirical study using a sample of 30 Chinese provinces from 2013 to 2022, based on the BP neural network model and fuzzy-set Qualitative Comparative Analysis (fsQCA). The results show that among the elements through which the digital economy influences the construction of a modern circulation system, digital infrastructure is the primary factor, followed by digital industrialization, with industrial digitalization ranking last, thus verifying the hypothesis. There are two types of configurational paths for the digital economy’s empowerment of the modern circulation system: high-level and low-level configurations. The high-level configurations include two promotion models: comprehensive development and "infrastructure+digital industrialization" development. The low-level configurations include three hindrance models: overall deficiency, "infrastructure+X" deficiency, and only digital infrastructure deficiency. From the configurational paths, digital infrastructure is a necessary element for the digital economy to empower the construction of a modern circulation system and a prerequisite for the digital economy to achieve effective empowerment in the construction of the modern circulation system. This study deepens the identification of elements through which the digital economy empowers the construction of a modern circulation system and proposes specific configurational paths, providing differentiated and implementable digital empowerment solutions for the government and circulation enterprises.

Key words: digital economy, modern distribution system, BP neural network, fsQCA, configurational paths

CLC Number:

F724.7

ZHANG Wukang, ZHANG Chi. Study Research on the Identification of Elements and Path of Digital Economy Enabling the Construction of Modern Circulation System-Analysis based on BP neural network and fsQCA[J]. Journal of Guizhou University of Finance and Economics, 2026(01): 54-64.

References

[1] 高国生,叶林祥,支海兵.我国农产品流通效率时空演变、地区差异与收敛性[J].经济问题,2025(1):100~112.
[2] 李义华,吴露青.我国农产品冷链物流效率时空演化特征[J/OL].吉首大学学报(社会科学版), 2024-12-26:1~11.
[3] 龚雪.区域物流效率测度及影响因素分析[J].统计与决策,2022(12):112~116.
[4] 王晓东,谢莉娟.现代流通体系支撑构建新发展格局的政治经济学分析[J].教学与研究,2022(6):42~55.
[5] 蒙天成,周利国."双循环"新发展格局下现代流通体系发展态势与高质量推进策略[J].国际贸易,2021(8):46~53.
[6] 祝合良,杨光,王春娟.双循环新发展格局下现代流通体系建设思路[J].商业经济与管理,2021(4):5~16.
[7] 王雪峰,荆林波.构建"双循环"新格局建设现代流通体系[J].商业经济与管理,2021(2):5~15.
[8] 丁华,丁宁.交通基础设施对商贸流通效率的影响研究[J].商业经济与管理,2023(7):28~39.
[9] 俞彤晖,崔许锋.中国现代流通体系建设水平测度及时空演化特征研究[J].财贸研究,2023(7):1~15.
[10] 李健.数字经济、要素市场化与产业结构转型升级[J].统计与信息论坛,2024(5):31~44.
[11] 郑丽琳,刘东升.数字经济、知识溢出与企业创新[J].统计与信息论坛,2024(10):42~55.
[12] 盛斌,吕美静,朱鹏洲.数字经济与全国统一大市场建设:基于城市层面的研究[J].求是学刊,2024(3):1~18.
[13] 陈雨露.数字经济与实体经济融合发展的理论探索[J].经济研究,2023(9):22~30.
[14] 依绍华,吴顺利.数字化背景下流通业态创新与品质消费的非对称互促关系:供给主导抑或需求引领[J].财贸经济,2024 (5): 121~141.
[15] 黄梦涵,张卫国,兰秀娟.新型基础设施建设对经济高质量发展的影响:异质性与作用机制[J].经济问题探索,2023(8):19~35.
[16] 马费成,王淳洋.数字产业化的理论逻辑与实践路径[J].信息资源管理学报,2024(6):4~16.
[17] 付雅梅,任保平.中国产业数字化的理论逻辑、特征事实及突破路径[J].经济体制改革,2024(6):5~13.
[18] 王珂,郭晓曦.中国新质生产力水平、区域差异与时空演进特征[J].统计与决策,2024(9):30~36.
[19] 杨慧梅,江璐.数字经济、空间效应与全要素生产率[J].统计研究,2021(4):3~15.
[20] 王军,朱杰,罗茜.中国数字经济发展水平及演变测度[J].数量经济技术经济研究,2021(7):26~42.
[21] Li X,Wang J,Yang C.Risk Prediction in Financial Management of Listed Companies Based on Optimized BP Neural Network under Digital Economy[J].Neural Computing and Applications,2023(3):2045~2058.
[22] Li D J,Li Y Y,Li J X,et al.Gesture Recognition Based on BP Neural Network Improved by Chaotic Genetic Algorithm[J].International Journal of Automation and Computing,2018(3):267~276.
[23] Liu X,Guo J,Wang H,et al.Prediction of Stock Market Index Based on ISSA-BP Neural Network[J].Expert Systems with Applications,2022,204:117604.
[24] Zhang L,Wang F,Sun T,et al.A Constrained Optimization Method Based on BP Neural Network[J].Neural Computing and Applications,2018,29:413~421.
[25] 杜运周,李佳馨,刘秋辰,等.复杂动态视角下的组态理论与QCA方法:研究进展与未来方向[J].管理世界,2021(3):180~197;12~13.
[26] 许敬辉,王乃琦,郭富林.数字乡村发展水平评价指标体系构建与实证[J].统计与决策,2023(2):73~77.
[27] 孙景昊,何海燕.基于BP神经网络的高校国家重点实验室科技创新绩效影响因素研究[J].科学管理研究,2022(4):48~54.
[28] 侯冠宇,熊金武.数字经济对共同富裕的影响与提升路径研究:基于我国30个省份的计量与QCA分析[J].云南民族大学学报(哲学社会科学版),2023(3):89~99.
[29] 王颖,刘艺扬.什么样的制度产生高人力资本经济增长效应:一个基于动态QCA方法的研究[J].科学学研究,2024(2):289~299;334.
[30] Xie X,Wang H.How Can Open Innovation Ecosystem Modes Push Product Innovation Forward? An fsQCA analysis[J].Journal of Business Research,2020,108:29~41.
[31] 张明,陈伟宏,蓝海林.中国企业"凭什么"完全并购境外高新技术企业:基于94个案例的模糊集定性比较分析(fsQCA)[J].中国工业经济,2019(4):117~135.